A novel adaptive finite-time tracking control for robotic manipulators using nonsingular terminal sliding mode and RBF neural networks

This paper presents a novel adaptive terminal sliding mode controller for the trajectory tracking of robotic manipulators using radial basis function neural networks (RBFNNs). First, a modified terminal sliding mode (TSM) surface is approached to avoid the singularity problem of conventional TSM. Then, a nonsingular TSM control is designed for joint position tracking of a robotic manipulator. In the control scheme, fully tuned RBFNNs are adopted to approximate the nonlinear unknown dynamics of the robotic manipulator. Adaptive learning algorithms are derived to allow online adjustment of the output weights, the centers and the variances in the RBFNNs. Meanwhile, a continuous robust control term is added to eliminate chattering efforts in the sliding mode control (SMC) system. The stability and finite-time convergence of the closed-loop system are established by using Lyapunov theory. Finally, the simulation results of a two-link robotic manipulator are presented to demonstrate the effectiveness of the proposed control method.